Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    phrases related to the history or track record of entities

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to historical performance or track records

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    idden
    -0.71
    uri
    -0.70
    insk
    -0.68
    agers
    -0.67
    imeters
    -0.67
    wolves
    -0.66
    wered
    -0.66
    ower
    -0.66
    asus
    -0.65
    ando
    -0.65
    POSITIVE LOGITS
     documented
    0.77
     revolving
    0.77
     dating
    0.74
     dealings
    0.72
    acqu
    0.72
     convictions
    0.72
     aversion
    0.70
     associ
    0.70
     Incarn
    0.69
     resemblance
    0.69
    Act Density 0.123%

    No Known Activations